{"id":"W2157864803","doi":"","title":"Action-Gap Phenomenon in Reinforcement Learning","year":2011,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Action (physics); Phenomenon; Bounded function; Q-learning; Bellman equation; Function (biology); Value (mathematics); Mathematics; Reinforcement; Computer science; Mathematical optimization; Artificial intelligence; Statistics; Mathematical analysis; Physics; Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009284993,0.0003566885,0.0003332339,0.0007342233,0.0002502505,0.0002224502,0.001367574,0.0002211498,0.0001161324],"category_scores_gemma":[0.0001763299,0.000383438,0.0001042842,0.0009577348,0.00006362168,0.001084617,0.0005775162,0.0008173765,0.0001126057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007129125,"about_ca_system_score_gemma":0.0001919833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004657289,"about_ca_topic_score_gemma":0.0004357029,"domain_scores_codex":[0.9971056,0.0001744749,0.0006710821,0.0005699246,0.0005202644,0.000958628],"domain_scores_gemma":[0.9981421,0.00008716878,0.0003415653,0.001075878,0.00009302535,0.000260315],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004558981,0.0001203507,0.03892342,0.00003559854,0.00003804449,0.00008261863,0.002870473,0.8165485,0.00206654,0.1233036,0.0003105552,0.01565472],"study_design_scores_gemma":[0.0005910658,0.0004264032,0.02368588,0.00006029304,0.000009979623,0.00004170226,0.0001816802,0.964685,0.004902469,0.001865433,0.003002122,0.0005480355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009943073,0.0001318366,0.9705572,0.0004411827,0.0002256766,0.0005303891,3.1975e-7,0.0009728189,0.01719757],"genre_scores_gemma":[0.8610929,0.0001473944,0.134382,0.0008015748,0.00005926624,0.0002263217,0.000006906329,0.0000430181,0.003240613],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8511498,"threshold_uncertainty_score":0.9998618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03411165688407607,"score_gpt":0.2483852345278482,"score_spread":0.2142735776437722,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}